Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating combinations or mixtures of elements or factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antly
    -0.17
    irit
    -0.16
    ampa
    -0.16
    vre
    -0.15
    alley
    -0.14
    ÏĢα
    -0.14
    alse
    -0.14
    ardy
    -0.14
    inally
    -0.14
    deaux
    -0.14
    POSITIVE LOGITS
    -toggler
    0.17
    heim
    0.17
    bild
    0.15
     incremental
    0.15
    ichert
    0.14
    ,strlen
    0.14
     Quantum
    0.14
    oni
    0.13
    eting
    0.13
     dil
    0.13
    Act Density 0.012%

    No Known Activations